© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 28-LLAMASCOPE-RES-32K
    11. 30138
    Prev
    Next
    INDEX
    Explanations

    actions and phrases related to behavior and conduct

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dans
    -0.27
    within
    -0.27
     within
    -0.26
    inside
    -0.25
     chez
    -0.23
     Within
    -0.23
    Within
    -0.23
     nella
    -0.22
     inside
    -0.22
     elsewhere
    -0.21
    POSITIVE LOGITS
     in
    0.38
    -in
    0.31
     Ïĥε
    0.19
    (in
    0.18
     inplace
    0.18
    _in
    0.17
    ,in
    0.17
     inorder
    0.17
    Âłin
    0.16
     à¹ĥà¸Ļ
    0.16
    Activations Density 0.371%

    No Known Activations